Every mod

All nine kinds in one list: what an agent loads, what it runs, what it reads and what bundles the rest. 415,086 of them, each with its token cost per session, a security scan with the line that triggered it, and whether it is the original or one of the copies.

upstream-watch

3889

DougTrajano/pydantic-ai-skills

Command Claude Code

Review pydantic-ai and pydantic-ai-harness releases published since the last watch entry, and record a verdict in .github/upstream-watch.md.

not rated 371 +2 changed 9d ago A 31 tokens original MIT

chrome-cdp

3890

IgorWarzocha/howaboua-pi-stuff

Skill Claude CodeCodex

Chrome CDP inspection/control: rendered pages, authenticated tabs, navigation, interaction, DOM/accessibility state, network, screenshots. Use when browser-rendered evidence or existing browser state matters.

not rated 373 +13 today A SkillSpector: pass 41 tokens original MIT

cognitionai/deepwiki

3891

opengovsg/FormSG

MCP server Claude CodeCodexCursor +2

DeepWiki's hosted MCP server: AI-generated documentation of public GitHub repositories the agent can query. Remote server at mcp.deepwiki.com.

not rated 371 yesterday A tokens not measured

posting-20-00

3894

justxor/MachineLearningRoadmap

Skill Claude CodeCodex

An instruction to open a specific X.com profile in Chrome. X.com is the website formerly known as Twitter.

not rated 370 +6 3mo ago A 21 tokens

zamesin/Next-Move-Theory-Canon-and-Skills

Skill Claude Code

Generate the strongest possible Value Proposition for a chosen segment using Ivan Zamesin's AJTBD / Next Move Theory methodology (distinct from generic Christensen JTBD). Input — a /nmt-market-research result OR a manual segment+Jobs description. The skill extracts the segment's dominant success criteria, builds the…

not rated 372 +9 changed yesterday A 193 tokens

pstack

3896

michael-denyer/pstack-claude

Plugin Claude Code

Bundles 56 skills, 2 agents, 1 hook · 2,777 tokens together

if you want to go fast, go deep first. pstack helps you write less, but higher quality code. rigorous agent workflows you can parallelize with confidence. Ported from cursor/plugins/pstack to Claude Code. Original pstack by Lauren Tan (poteto).

not rated 389 +125 changed yesterday A tokens not measured original MIT

writing-helper

3897

AIGNE-io/aigne-framework

Skill Claude CodeCodex

A versatile writing assistant that helps compose, improve, and transform text for various purposes including emails, letters, reports, social media, and more.

not rated 369 +1 7mo ago A 31 tokens

tcx-brain

3899

monarchjuno/tradingcodex

Skill Codex

Author and manage TradingCodex Investment Brains. Use when the user asks to put principles or a Wiki insight into a Brain; create, inspect, revise, or validate a user-owned investment-brain- source; or install, update, activate, deactivate, roll back, or remove a managed Brain. Natural-language source authoring is…

not rated 369 +1 1mo ago A SkillSpector: pass 96 tokens original Apache-2.0

omni

3900

fajarhide/omni

Plugin Claude Code

Bundles 1 skill · 61 tokens together

Install OMNI, verify it, and read the markers it leaves when it shortens command output.

not rated 369 +2 changed 10d ago A tokens not measured copy · 89% Apache-2.0

writing

3901

Anbeeld/WRITING.md

Skill Claude CodeCodex

Draft, revise, audit, or transform human-facing prose: articles, blogs, documentation, criticism, essays, email, marketing and SEO copy, summaries, scripts, application materials, and UI text. Excludes code comments, commit messages, and private notes.

not rated 369 +3 1mo ago A SkillSpector: pass 54 tokens original MIT

reflexio-embedded

3902

ReflexioAI/reflexio

Skill Claude CodeCodex

Captures user facts and procedural corrections into .reflexio/ so the agent learns across sessions. Use when: (1) user states a preference, fact, config, or constraint; (2) user corrects the agent and confirms the fix with an explicit 'good'/'perfect' or by moving on without re-correcting for 1-2 turns; (3) at start…

not rated 370 +4 today A SkillSpector: warn 102 tokens original Apache-2.0

autopilot

3903

nick-vels/skills

Skill Claude Code

An end-to-end building workflow for users who describe an app, website, bot, or feature and want a finished project in one conversation.

not rated 370 +23 26d ago A Socket: passSnyk: warnSkillSpector: pass 141 tokens original MIT

greeting

3904

anthropics/anthropic-sdk-ruby

Skill Claude CodeCodex ✓ vendor

Replaces ordinary greetings with nautical ones.

not rated 369 +3 3d ago A 11 tokens copy · 100% MIT

oil-oil/codex-deepseek-subagent

Skill Codex

A configuration tool for adding and maintaining DeepSeek V4 Flash or V4 Pro as a native sub-agent in the Codex desktop app. It handles model selection, credentials, testing, repair, disabling, and removal.

not rated 368 +4 changed 4d ago A Socket: passSnyk: warnSkillSpector: pass 71 tokens original MIT

data-analysis

3906

qaml-ai/camelAI

Skill Claude CodeCodex

Analyze data using Python and SQL tools. Use when the user asks to process CSVs, Excel, Parquet, PDFs, Word docs, or PowerPoint files, query databases (PostgreSQL, MySQL, SQLite, SQL Server, BigQuery), create charts or visualizations, or perform any data analysis. For live dashboards or data apps, read the…

not rated 369 +1 today A SkillSpector: pass 80 tokens original MIT

getopenpost/openpost

Skill Claude CodeCodex

Guidance on writing fast, robust, modern Svelte code. Load this skill whenever in a Svelte project and asked to write/edit or analyze a Svelte component or module. Covers reactivity, event handling, styling, integration with libraries and more.

not rated 489 +267 today A 59 tokens AGPL-3.0

tokenbender/agent-guides

Skill Claude CodeCodex

Estimate whether an AI model can complete a task and how long it will take, using METR-style time-horizon modeling. Use when scoping agent work, deciding if a task is within reach, planning retries/parallelism, estimating wall-clock time for SWE/MLE/math tasks, or answering "can you do this" / "how long will this…

not rated 367 +1 1mo ago A SkillSpector: pass 84 tokens original Apache-2.0

pymol-visualization

3909

ChatMol/ChatMol

Skill Claude CodeCodex

Generate publication-quality molecular visualization images using PyMOL. Use this skill whenever the user mentions PyMOL, molecular visualization, protein rendering, structure figures, PDB visualization, ray tracing molecules, or wants to create images of proteins, ligands, binding sites, protein-protein interactions…

not rated 367 6mo ago A 174 tokens original MIT

agent-browser

3910

brianlovin/agent-config

Skill Claude Code

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a…

not rated 368 +1 5mo ago A Socket: passSnyk: fail 108 tokens

LambdaTest/agent-skills

Skill Claude CodeCodex

Automatically generate comprehensive test cases from API definitions, endpoint descriptions, OpenAPI/Swagger specs, Postman collections, or raw HTTP request/response examples. Use this skill whenever the user mentions generating tests from APIs, writing test cases for REST endpoints, API testing, creating test suites…

not rated 368 +1 3d ago A SkillSpector: warn 182 tokens original MIT

vault

3912

smixs/agent-second-brain

Plugin Claude Code

Bundles 4 skills, 2 agents · 340 tokens together

Voice-first personal assistant for capturing thoughts and tasks via Telegram, with goal tracking and Obsidian integration.

not rated 367 +1 1mo ago A tokens not measured original MIT

At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: